# Adversarial Counterfactual Learning and Evaluation for Recommender System

arXiv: https://arxiv.org/abs/2012.02295 · HTML: https://mlsanity.com/paper/2012.02295/

## Key facts

- Cited by 16 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 8 Nov 2020.

## Built on by (most cited first, 16 of 16)

- [Learning from Counterfactual Links for Link Prediction](https://mlsanity.com/paper/2106.02172/) (2021)
- [Understanding the role of importance weighting for deep learning](https://mlsanity.com/paper/2103.15209/) (2021)
- [Rethinking Neural vs. Matrix-Factorization Collaborative Filtering: the Theoretical Perspectives](https://mlsanity.com/paper/2110.12141/) (2021)
- [RMT-Net: Reject-aware Multi-Task Network for Modeling Missing-not-at-random Data in Financial Credit Scoring](https://mlsanity.com/paper/2206.00568/) (2022)
- [Investigating the Adversarial Robustness of Density Estimation Using the Probability Flow ODE](https://mlsanity.com/paper/2310.07084/) (2023)
- [Addressing Missing Data Issue for Diffusion-based Recommendation](https://mlsanity.com/paper/2505.12283/) (2025)
- [Causal Structure Learning with Recommendation System](https://mlsanity.com/paper/2210.10256/) (2022)
- [Uncertainty Calibration for Counterfactual Propensity Estimation in Recommendation](https://mlsanity.com/paper/2303.12973/) (2023)
- [REST: Debiased Social Recommendation via Reconstructing Exposure Strategies](https://mlsanity.com/paper/2201.04952/) (2022)
- [Mitigating Frequency Bias in Next-Basket Recommendation via Deconfounders](https://mlsanity.com/paper/2211.09072/) (2022)
- [Pretrained Embeddings for E-commerce Machine Learning: When it Fails and Why?](https://mlsanity.com/paper/2304.04330/) (2023)
- [The Importance of Causality in Decision Making: A Perspective on Recommender Systems](https://mlsanity.com/paper/2410.01822/) (2024)
- [ShiJianBench: From Dialogue to Decision for Long-Horizon Evaluation of Investment Advisors](https://mlsanity.com/paper/2608.01204/) (2026)
- [Towards the D-Optimal Online Experiment Design for Recommender Selection](https://mlsanity.com/paper/2110.12132/) (2021)
- [Reconsidering Learning Objectives in Unbiased Recommendation with Unobserved Confounders](https://mlsanity.com/paper/2206.03851/) (2022)
- [CFLight: Enhancing Safety with Traffic Signal Control through Counterfactual Learning](https://mlsanity.com/paper/2512.09368/) (2025)

## Abstract (arXiv)

The feedback data of recommender systems are often subject to what was exposed to the users; however, most learning and evaluation methods do not account for the underlying exposure mechanism. We first show in theory that applying supervised learning to detect user preferences may end up with inconsistent results in the absence of exposure information. The counterfactual propensity-weighting approach from causal inference can account for the exposure mechanism; nevertheless, the partial-observation nature of the feedback data can cause identifiability issues. We propose a principled solution by introducing a minimax empirical risk formulation. We show that the relaxation of the dual problem can be converted to an adversarial game between two recommendation models, where the opponent of the candidate model characterizes the underlying exposure mechanism. We provide learning bounds and conduct extensive simulation studies to illustrate and justify the proposed approach over a broad range of recommendation settings, which shed insights on the various benefits of the proposed approach.